RESUMEN
OBJECTIVE: Computed tomography is considered the gold-standard imaging tool to evaluate spinal implant accuracy. However, there are no studies that evaluate the accuracy of robotic sacroiliac joint (SIJ) implant placement using CT to date. The aim of this study was to compare the accuracy of implant placement on CT between robotic and fluoroscopic navigation for SIJ fusion and the subsequent complications and clinical outcomes of suboptimally placed screws. METHODS: A retrospective analysis of SIJ fusions utilizing either robotic or fluoroscopic guidance at a single institution was conducted from 2014 to 2023. Implant placement accuracy was evaluated on intra- or postoperative CT. Primary endpoints were SIJ screw placement accuracy and complications. Secondary endpoints were pain status at the first and second follow-ups and rates of 2-year revision surgery. Statistical analysis was performed using chi-square tests. RESULTS: Sixty-nine patients who underwent 78 SIJ fusions were included, of which 63 were robotic and 15 were fluoroscopic. The mean age of the cohort at the time of surgery was 55.9 ± 14.2 years, and 35 patients (50.7%) were female. There were 135 robotically placed and 34 fluoroscopically placed implants. A significant difference was found in implant placement accuracy between robotic and fluoroscopic fusion (97.8% vs 76.5%, p < 0.001). When comparing optimal versus suboptimal implant placement, no difference was found in the presence of 30-day complications (p = 0.98). No intraoperative complications were present in this cohort. No difference was found in subjective pain status at the first (p = 0.69) and second (p = 0.45) follow-ups between optimal and suboptimal implant placement. No patients underwent 2-year revision surgery. CONCLUSIONS: Use of robotic navigation was significantly more accurate than the use of fluoroscopic navigation for SIJ implant placement. Complications overall were low and not different between optimally and suboptimally placed implants. Suboptimally placed implants did not differ in degree of subjective pain improvement or rates of revision surgery postoperatively.
RESUMEN
OBJECTIVE: Achieving appropriate spinopelvic alignment has been shown to be associated with improved clinical symptoms. However, measurement of spinopelvic radiographic parameters is time-intensive and interobserver reliability is a concern. Automated measurement tools have the promise of rapid and consistent measurements, but existing tools are still limited to some degree by manual user-entry requirements. This study presents a novel artificial intelligence (AI) tool called SpinePose that automatically predicts spinopelvic parameters with high accuracy without the need for manual entry. METHODS: SpinePose was trained and validated on 761 sagittal whole-spine radiographs to predict the sagittal vertical axis (SVA), pelvic tilt (PT), pelvic incidence (PI), sacral slope (SS), lumbar lordosis (LL), T1 pelvic angle (T1PA), and L1 pelvic angle (L1PA). A separate test set of 40 radiographs was labeled by four reviewers, including fellowship-trained spine surgeons and a fellowship-trained radiologist with neuroradiology subspecialty certification. Median errors relative to the most senior reviewer were calculated to determine model accuracy on test images. Intraclass correlation coefficients (ICCs) were used to assess interrater reliability. RESULTS: SpinePose exhibited the following median (interquartile range) parameter errors: SVA 2.2 mm (2.3 mm) (p = 0.93), PT 1.3° (1.2°) (p = 0.48), SS 1.7° (2.2°) (p = 0.64), PI 2.2° (2.1°) (p = 0.24), LL 2.6° (4.0°) (p = 0.89), T1PA 1.1° (0.9°) (p = 0.42), and L1PA 1.4° (1.6°) (p = 0.49). Model predictions also exhibited excellent reliability at all parameters (ICC 0.91-1.0). CONCLUSIONS: SpinePose accurately predicted spinopelvic parameters with excellent reliability comparable to that of fellowship-trained spine surgeons and neuroradiologists. Utilization of predictive AI tools in spinal imaging can substantially aid in patient selection and surgical planning.
RESUMEN
PURPOSE: The estimated incidence of pituitary adenomas in the general population is 10-30%, yet radiographic diagnosis remains a challenge. Diagnosis is complicated by the heterogeneity of radiographic features in both normal (e.g. complex anatomy, pregnancy) and pathologic states (e.g. primary endocrinopathy, hypophysitis). Clinical symptoms and laboratory testing are often equivocal, which can result in misdiagnosis or unnecessary specialist referrals. Computer vision models can aid in pituitary adenoma diagnosis; however, a major challenge to model development is the lack of dedicated pituitary imaging datasets. We hypothesized that deep volumetric segmentation models trained to extract the sellar and parasellar region from existing whole-brain MRI scans could be used to generate a novel dataset of pituitary imaging. METHODS: Six open-source whole-brain MRI datasets, created for research purposes, were included for model development. Deep learning-based volumetric segmentation models were trained using 318 manually annotated MRI scans from a single open-source MRI dataset. Out-of-distribution volumetric segmentation performance was then tested on 418 MRIs from five held-out research datasets. RESULTS: On our annotated images, agreement between manual and model volumetric segmentations was high. Dice scores (a measure of overlap) ranged 0.76-0.82 for both in-distribution and out-of-distribution model testing. In total, 6,755 MRIs from six data sources were included in the final generated pituitary dataset. CONCLUSIONS: We present the first and largest dataset of pituitary imaging constructed using existing MRI data and deep volumetric segmentation models trained to identify sellar and parasellar anatomy. The model generalizes well across patient populations and MRI scanner types. We hope our pituitary dataset will be an integral part of future machine learning research on pituitary pathologies.